[R-sig-ME] Interpreting the output of summary() of a glmer-object
Hans Ekbrand
hans at sociologi.cjb.net
Mon Sep 24 16:16:11 CEST 2012
Dear list,
First, I have a very simple question. In the summary output of a
glmer-object, What does the "Variance" and "Std.Dev" mean for the
Random effects? What is the scale for these measures?
load(url("http://sociologi.cjb.net/temp/a.strange.df.RData"))
my.fit.1 <- glmer(MV744A ~ (1|MV024), data = a.strange.df, family = "binomial")
summary(my.fit.1)
Generalized linear mixed model fit by the Laplace approximation
Formula: MV744A ~ (1 | MV024)
Data: a.strange.df
AIC BIC logLik deviance
76209 76227 -38102 76205
Random effects:
Groups Name Variance Std.Dev.
MV024 (Intercept) 0.40558 0.63685
Number of obs: 73601, groups: MV024, 29
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -1.4187 0.1191 -11.91 <2e-16 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
I think that I understand that if the Variance term, here 0.40558 is
low relative to the Std.Dev, there is not much variation caught by the
random term (in this case where the random term represents "Regions",
few Regions would then significantly differ from the grand mean). Here
we have a big underlying n, which might explain that most Regions did
signficantly differ from the mean.
dotplot(ranef(my.fit.1, postVar = TRUE))
Secondly, after adding several fixed terms, each with a substantial effect, I
would (given my vague understanding of what the "Variance" term means)
expect the "Variance" of the random effect to decrease, but on the
contrary it increased:
summary(my.fit.5 <- glmer(MV744A ~ (1|MV024) + MV025 + MV106 + MV012 + MV130, data = a.strange.df, family = "binomial"))
Generalized linear mixed model fit by the Laplace approximation
Formula: MV744A ~ (1 | MV024) + MV025 + MV106 + MV012 + MV130
Data: a.strange.df
AIC BIC logLik deviance
73327 73483 -36646 73293
Random effects:
Groups Name Variance Std.Dev.
MV024 (Intercept) 0.46855 0.6845
Number of obs: 73560, groups: MV024, 29
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -0.7491070 0.1343065 -5.58 2.44e-08 ***
MV025Rural 0.4423018 0.0198776 22.25 < 2e-16 ***
MV106Primary -0.1829852 0.0306670 -5.97 2.42e-09 ***
MV106Secondary -0.5743379 0.0263945 -21.76 < 2e-16 ***
MV106Higher -1.2945147 0.0385589 -33.57 < 2e-16 ***
MV012 -0.0145262 0.0008938 -16.25 < 2e-16 ***
MV130Muslim 0.3079549 0.0276753 11.13 < 2e-16 ***
MV130Christian -0.2949242 0.0431780 -6.83 8.47e-12 ***
MV130Sikh -0.2605808 0.1087276 -2.40 0.01655 *
MV130Buddhist/Neo-Buddhist -0.0139619 0.0830028 -0.17 0.86642
MV130Jain -0.3624429 0.1909181 -1.90 0.05764 .
MV130Jewish -8.9103460 63.6027289 -0.14 0.88859
MV130Parsi/Zoroastrian -9.6231061 90.8921529 -0.11 0.91568
MV130No religion -0.5553414 0.7918028 -0.70 0.48308
MV130Donyi polo 0.7034558 0.2266543 3.10 0.00191 **
MV130Other -0.0718436 0.0890363 -0.81 0.41972
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Sure, the Std.Dev of the random effect also increased (from 0.63685 to
0.6845) but still, isn't the increase of the variance of random effect
(from 0.40558 to 0.46855) rather odd here?
How do you interpret an increase in the random effect after adding
perfectly fine explanatory fixed terms to the model?
BTW. The dependent variable MV744A measures an attitude, and MV025 is
type of area (Urban/Rural), MV106 is educational level, MV012 is age,
MV130 is religion.
The caterpillar plot for my.fit.5, shows all regions except 3 of them
differ signifcantly from the mean, even when controlling for the fixed
terms.
dotplot(ranef(my.fit.5, postVar = TRUE))
Any hints, or reading tips, greatly appreciated.
Kind regards,
--
Hans Ekbrand
Department of sociology and workscience
University of Gothenburg, Sweden.
More information about the R-sig-mixed-models
mailing list